yo-steven/skills-exploration-20260522 - Página 2

resiliency

Resiliency features in Megatron Bridge including fault tolerance, straggler detection, in-process restart, preemption, and re-run state machine.

Idioma del texto original: inglés

verl-e2e-testing

External verl end-to-end validation workflow for Megatron-Bridge model/provider changes. Covers running a small verl Megatron backend job from a Bridge checkout, choosing LoRA/DDP plus optional save/resume and parallelism variants, setting PYTHONPATH so verl…

Idioma del texto original: inglés

bump-base-image

Bump the NVIDIA PyTorch base image (`nvcr.io/nvidia/pytorch:<YY.MM>-py3`) used by Megatron-LM CI. Covers the two pin sites (GitHub CI in `docker/.ngc_version.dev` and GitLab CI in `.gitlab/stages/01.build.yml`), the post-bump CI loop (re-run functional tests,…

Idioma del texto original: inglés

deployment

Serve a quantized or unquantized LLM checkpoint as an OpenAI-compatible API endpoint using vLLM, SGLang, or TRT-LLM. Use when user says "deploy model", "serve model", "start vLLM server", "launch SGLang", "TRT-LLM deploy", "AutoDeploy", "benchmark…

Idioma del texto original: inglés

evaluation

Evaluates accuracy of quantized or unquantized LLMs using NeMo Evaluator Launcher (NEL). Triggers on "evaluate model", "benchmark accuracy", "run MMLU", "evaluate quantized model", "accuracy drop", "run nel". Handles deployment, config generation, and…

Idioma del texto original: inglés

launching-evals

Run, monitor, analyze, and debug LLM evaluations via nemo-evaluator-launcher. Covers running evaluations, checking status and live progress, debugging failed runs, exporting artifacts and logs, and analyzing results. ALWAYS triggers on mentions of running…

Idioma del texto original: inglés

monitor

Monitor submitted jobs (PTQ, evaluation, deployment) on SLURM clusters. Use when the user asks "check job status", "is my job done", "monitor my evaluation", "what's the status of the PTQ", "check on job <slurm_job_id>", or after any skill submits a…

Idioma del texto original: inglés

ptq

This skill should be used when the user asks to "quantize a model", "run PTQ", "post-training quantization", "NVFP4 quantization", "FP8 quantization", "INT8 quantization", "INT4 AWQ", "quantize LLM", "quantize MoE", "quantize VLM", or needs to produce a…

Idioma del texto original: inglés

byob

Create custom LLM evaluation benchmarks using the BYOB decorator framework. Use when the user wants to (1) create a new benchmark from a dataset, (2) pick or write a scorer, (3) compile and run a BYOB benchmark, (4) containerize a benchmark, or (5) use…

Idioma del texto original: inglés

accessing-mlflow

Query and browse evaluation results stored in MLflow. Use when the user wants to look up runs by invocation ID, compare metrics across models, fetch artifacts (configs, logs, results), or set up the MLflow MCP server. ALWAYS triggers on mentions of MLflow,…

Idioma del texto original: inglés

launching-evals

Run, monitor, analyze, and debug LLM evaluations via nemo-evaluator-launcher. Covers running evaluations, checking status and live progress, debugging failed runs, exporting artifacts and logs, and analyzing results. ALWAYS triggers on mentions of running…

Idioma del texto original: inglés

nel-assistant

Interactive config wizard for NeMo Evaluator Launcher (NEL). Use when the user wants to create a new evaluation config from scratch, set up an evaluation from existing configs, or modify a NEL config (deployment, tasks, multi-node, interceptors). ALWAYS…

Idioma del texto original: inglés

nemo-gym-debugging

Use when debugging a Nemo Gym run or reward profiling job. Covers rollout collection failures, empty or partial JSONL outputs, stale materialized inputs, verifier/schema errors, Ray or Slurm issues, vLLM readiness, judge failures, tool/sandbox failures, cache…

Idioma del texto original: inglés

nemo-gym-docs

Maintain the NeMo Gym Fern docs site — add, update, move, or remove pages under fern/. Use for any documentation change. Triggered by: "edit docs", "add doc page", "update docs", "rename page", "fix broken link", "add redirect", "preview docs", "publish…

Idioma del texto original: inglés

nemo-gym-pivot-datasets

Use when creating, validating, or documenting Nemo Gym pivot datasets from rollout, trajectory, chat-completion, Responses API, or tool-call artifacts. Covers Gym Responses-style row conversion, pivot selection, single-step tool-use configs, agent_ref…

Idioma del texto original: inglés

nemo-gym-reward-profiling

Use to help users get started with Nemo Gym reward profiling. Covers the basic ng_run, ng_collect_rollouts, and ng_reward_profile workflow, repeated rollouts, materialized inputs, rollout JSONL artifacts, task and rollout identity, output inspection, partial…

Idioma del texto original: inglés

auto-research

Autonomous NeMo-RL research agent workflow for directed hypothesis testing and open-ended discovery. Guides agents through the full experiment lifecycle: understanding recipes and environments, wiring RL or NeMo-gym runs, launching reproducible baselines and…

Idioma del texto original: inglés

brev-etiquette

Brev instance operating guidance for NeMo-RL agents working in /home/ubuntu/RL with limited workspace disk, a larger /ephemeral volume, and optional /home/ubuntu/RL/.env secrets. Use when running auto-research campaigns, experiments, training jobs, model or…

Idioma del texto original: inglés

build-and-dependency

Build and dependency management for NeMo-RL. Covers Docker image building and running, uv usage, venv setup, and adding dependencies.

Idioma del texto original: inglés

config-conventions

Configuration conventions for NeMo-RL. YAML is the single source of truth for defaults. Covers TypedDict usage, exemplar YAML updates, and forbidden default patterns.

Idioma del texto original: inglés

docs

Documentation conventions for NeMo-RL. Covers docs/index.md updates and docstring format.

Idioma del texto original: inglés

error-handling

Error handling guidelines for NeMo-RL. Covers exception specificity, minimal try bodies, and else blocks.

Idioma del texto original: inglés

launch-nemo-rl

Playbook for launching, monitoring, stopping, and debugging NeMo-RL recipes on a Kubernetes cluster via the nrl-k8s CLI. Covers ephemeral vs long-lived RayCluster modes, iterating on runs, and debugging hung or failed training jobs.

Idioma del texto original: inglés

linting-and-formatting

Code style guidelines for NeMo-RL (Python and shell). Covers naming, indentation, comments, docstrings, reflection avoidance, and uv usage.

Idioma del texto original: inglés

review-pr

Interactive code review for NVIDIA-NeMo/RL pull requests. Checks out PR locally, reads existing comments, applies coding guidelines from skills, previews findings, and posts review comments. Also supports reviewing the current branch locally.

Idioma del texto original: inglés

session-memory

Manage durable working-session memory for coding agents. Use when a user asks to preserve or recover agent context across disconnects, VS Code restarts, long-running work, handoffs, or any session where important state should be written periodically under the…

Idioma del texto original: inglés

nemoclaw-contributor-create-pr

Create GitHub pull requests that follow the NemoClaw PR template. Use when the user wants to create a new PR, submit code for review, open a pull request, or push changes for review. Trigger keywords - create PR, pull request, new PR, submit for review, open…

Idioma del texto original: inglés

nemoclaw-contributor-update-docs

Scan recent git commits for changes that affect user-facing behavior, then draft or update the corresponding documentation pages and refresh generated user skills for release prep. Use when docs have fallen behind code changes, after a batch of features…

Idioma del texto original: inglés

nemoclaw-skills-guide

Start here. Introduces what NemoClaw is, what agent skills are available, and which skill to use for a given task. Use when discovering NemoClaw capabilities, choosing the right skill, or orienting in the project. Trigger keywords - skills, capabilities, what…

Idioma del texto original: inglés

nemoclaw-user-agent-skills

Describes the agent skills shipped with NemoClaw and how to access them by cloning the repository. Use when users ask about AI agent support, coding assistant integration, or the .agents/skills/ directory. Trigger keywords - nemoclaw agent skills, ai coding…

Idioma del texto original: inglés

nemoclaw-user-configure-inference

Connects NemoClaw to a local inference server. Use when setting up Ollama, vLLM, TensorRT-LLM, NIM, or any OpenAI-compatible local model server with NemoClaw. Trigger keywords - nemoclaw local inference, ollama nemoclaw, vllm nemoclaw, local model server,…

Idioma del texto original: inglés

nemoclaw-user-configure-security

Presents a risk framework for every configurable security control in NemoClaw. Use when evaluating security posture, reviewing sandbox security defaults, or assessing control trade-offs. Trigger keywords - nemoclaw security best practices, sandbox security…

Idioma del texto original: inglés

nemoclaw-user-deploy-remote

Explains how to run NemoClaw on a remote GPU instance, including the deprecated Brev compatibility path and the preferred installer plus onboard flow. Use when deploying NemoClaw to a remote VM, onboarding a Brev instance, or migrating away from the legacy…

Idioma del texto original: inglés

nemoclaw-user-get-started

Installs NemoClaw, launches a sandbox, and runs the first agent prompt. Use when onboarding, installing, or launching a NemoClaw sandbox for the first time. Trigger keywords - nemoclaw quickstart, install nemoclaw openclaw sandbox, nemohermes quickstart,…

Idioma del texto original: inglés

nemoclaw-user-manage-policy

Adds, removes, or modifies allowed endpoints in the sandbox policy. Use when customizing network policy, changing egress rules, or configuring sandbox endpoint access. Trigger keywords - customize nemoclaw network policy, sandbox egress policy configuration,…

Idioma del texto original: inglés

nemoclaw-user-manage-sandboxes

Explains operational tasks after the quickstart: listing sandboxes, status and health checks, logs, diagnostics, port forwards, multiple sandboxes, credential reset, rebuilds, network presets, upgrades, and uninstall. Trigger keywords - manage nemoclaw…

Idioma del texto original: inglés

nemoclaw-user-monitor-sandbox

Inspects sandbox health, traces agent behavior, and diagnoses problems. Use when monitoring a running sandbox, debugging agent issues, or checking sandbox logs. Trigger keywords - monitor nemoclaw sandbox, debug nemoclaw agent issues.

Idioma del texto original: inglés

nemoclaw-user-overview

Explains how OpenClaw, OpenShell, and NemoClaw form the ecosystem, NemoClaw's position in the stack, what NemoClaw adds beyond the community sandbox, and when to prefer NemoClaw versus integrating OpenShell and OpenClaw directly. Use when users ask about the…

Idioma del texto original: inglés

nemoclaw-user-reference

Describes the NemoClaw plugin and blueprint architecture and how they orchestrate the OpenClaw sandbox. Use when looking up architecture, plugin structure, or blueprint design. Trigger keywords - nemoclaw architecture, nemoclaw plugin blueprint structure,…

Idioma del texto original: inglés

nemotron-voice-agent-deploy

Deploy Nemotron Voice Agent on Workstation (x86), Jetson Thor, or Cloud NIMs. Real-time speech-to-speech using NVIDIA ASR, TTS, LLM with WebRTC/WebSocket transport.

Idioma del texto original: inglés